BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Statistics
SUMMARY:Analysis and Forecasting of Locally Stationary Tim
e Series - Guy Nason\, University of Bristol
DTSTART;TZID=Europe/London:20141121T160000
DTEND;TZID=Europe/London:20141121T170000
UID:TALK54674AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/54674
DESCRIPTION:Faced with a new time series a statistician has ma
ny questions to ask. What kind of models are appro
priate? Is the sampling rate appropriate? Is the s
eries stationary? Are nonlinear models appropriate
? How can I produce good forecasts? This talk adve
rtises a collection of tools that can provide answ
ers or partial answers to some of these questions
in situations where it is suspected that the under
lying time series is not stationary. We shall summ
arize some of the theory underlying these new meth
ods and also demonstrate their performance in simu
lated situations. Finally\, we will show these too
ls in action on some time series recorded on the e
conomy and from the field of wind energy.
LOCATION:MR12\, Centre for Mathematical Sciences\, Wilberf
orce Road\, Cambridge
CONTACT:
END:VEVENT
END:VCALENDAR